JPH09329488A - Abnormality diagnosis - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable easy identification of a monitoring object in a abnormal behavior by using an expression in a symmetrized dotted pattern formed of an acoustic signal sampled by a microphone. SOLUTION: An acoustic signal collected by the microphone 14 is sampled by sampling means such as a noise meter 16 in a predetermined period, subjected to data conversion by an analogue/digital converter 18 and then transmitted to a signal processing section 19. In the signal processing section 19, the sampled acoustic signal is plotted on polar coordinates to obtain a dotted pattern. In such a manner, the acoustic signal transformed into the dotted pattern is displayed on an image screen of a display apparatus such as CRT. In displaying a dotted pattern in a visual manner, if a dotted pattern in a normal condition 20a and a dotted patter in diagnosis 20b are simultaneously displayed on the same image screen, distinction of an abnormal pattern can be executed in a easier way.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an equipment abnormality diagnosing apparatus and method, and in particular, equipment abnormality capable of easily diagnosing equipment abnormality such as a rotating machine installed in an arbitrary equipment space. The present invention relates to a diagnostic device and method.

[0002]

2. Description of the Related Art Conventionally, a predetermined sensor (for example, vibration Sensor,
Install a temperature sensor, acoustic sensor, etc.) near the equipment,
There is known a method of diagnosing abnormality of equipment by measuring vibration, temperature, or sound of the equipment and determining whether or not those measured values deviate from preset threshold values. .

There is also a method in which an operator who is skilled in equipment maintenance directly touches equipment equipment such as a rotating machine without using the above-mentioned automatic diagnosis apparatus and empirically determines an abnormality of the equipment equipment by the touch. Well done.

[0004]

However, the above-mentioned conventional apparatus or method for diagnosing abnormality of equipment has the following problems, for example. 1. In general, the mounting position of each sensor is limited by design, so it may not always be possible to install the sensor at the optimum position where accurate measurement values can be obtained, and in some cases, mounting of the sensor itself may be impossible. . 2. When the number of objects to be monitored is large, such as a fan filter unit installed on the ceiling of a clean room, installing a sensor on each equipment causes an increase in initial cost and equipment installed adjacent to each other. Due to the influence of, accurate values cannot be obtained for each individual device. 3. In the case of a known automatic diagnosis system, the initial value of each equipment is often unknown, and its identification is difficult. In particular, when the number of monitored objects is large, the difficulty increases dramatically as the number of monitored objects increases. Further, even with a system having a large number of management points, it is difficult to easily follow up with equipment expansion. Further, even when a known automatic diagnosis system is introduced into an existing building, the initial value is unknown. 4. Not only manual diagnostic systems but also automatic diagnostic systems require skill to determine whether the equipment is normal or abnormal from the measured values, and it is easy for individual differences to occur and accurate. The diagnosis is difficult. 5. In the conventional diagnostic system, not only the manual diagnostic system but also the automatic diagnostic system has a relatively large number of processing steps and a large amount of work by the operator.

Therefore, the present invention has been made in view of the above-mentioned problems, and does not require special training or experience for diagnosing an abnormality of equipment and sets an initial value by a numerical value. Can be performed easily and reliably without individual differences, and even when a large number of equipments are installed, it is possible to measure multiple equipments simultaneously with a small number of sensors. It is also an object of the present invention to provide a new and improved abnormality diagnosis device and method for facility equipment, which has a high degree of freedom in the location of installation of the sensor and can easily narrow down abnormal equipment.

[0006]

In order to solve the above problems, according to a first aspect of the present invention, sound generated by one or more monitoring objects installed in an arbitrary equipment space is collected. There is provided an abnormality diagnosis device that collects sound by a sound device and diagnoses an abnormality of the monitored object based on the acoustic signal.
As described in claim 1, the abnormality diagnosis device includes a sampling means for sampling an acoustic signal at a predetermined cycle, and a normalizing means for setting a variation width of the acoustic signal sampled over a certain time interval as a reference value. , The acoustic signal (X
(T)) relative size (A) with respect to the reference value
(I)) in a polar coordinate system, converting a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt into argument angles (Θ (i), Φ (i)). A plotting means for plotting at least two dots (a (i), b (i)) which are line-symmetric with respect to at least one starting line of the polar coordinate system for one acoustic signal (X (t)). A display means for visually displaying the dot pattern plotted by the plotting means, and the abnormality of the monitored object is diagnosed according to the dot pattern displayed by the display means. If the display means is configured to display the normal dot pattern and the diagnostic dot pattern on the same surface (for example, on the same screen or on the same paper surface), visual comparison work can be performed more easily. It can be done easily and efficiently.

Further, the abnormality diagnosis device according to claim 2 is
Sampling means for sampling the acoustic signal in a predetermined cycle, standardizing means for setting a fluctuation range of the acoustic signal sampled over a certain time interval as a reference value, and acoustic signal (X) sampled at a certain time (t). (T)) relative size (A) with respect to the reference value
(I)) in a polar coordinate system, converting a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt into argument angles (Θ (i), Φ (i)). A plotting means for plotting at least two dots (a (i), b (i)) which are line-symmetric with respect to at least one starting line of the polar coordinate system for one acoustic signal (X (t)). A pattern recognition means for recognizing the dot pattern plotted by the plotting means, a dot pattern at the time of diagnosis recognized by the pattern recognition means and a previously acquired normal dot pattern for comparison, and the diagnosis And a comparison diagnosis means for diagnosing that the monitored object is abnormal when there is a deviation of a predetermined value or more between the dot pattern at normal time and the dot pattern at normal time. It is characterized in that was.

The polar coordinate system used to obtain a dot pattern is divided into a plurality of symmetrical regions by a plurality of (n) starting lines, and two dots (a (i), By plotting b (i)), for example, by plotting dots with respect to six symmetry axes (start lines), a snow crystal-like dot pattern can be obtained, and the pattern can be visually and visually recognized. This makes it possible to easily and reliably distinguish between a normal pattern and an abnormal pattern without setting a numerical initial value.

Further, according to a second aspect of the present invention, the sound generated by one or more objects to be monitored installed in an arbitrary equipment space is collected by a sound collecting device, and the sound signal is obtained. An abnormality diagnosing method for diagnosing an abnormality of the monitored object based on the above is provided. As described in claim 3, the abnormality diagnosis method includes a step of sampling an acoustic signal in a predetermined cycle; a step of setting a fluctuation range of the acoustic signal sampled in the step as a reference value; acoustic signal (X
(T)) relative size (A) with respect to the reference value
(I)) in a polar coordinate system, converting a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt into argument angles (Θ (i), Φ (i)). Plotting at least two dots (a (i), b (i)) that are line-symmetric with respect to at least one start line of the polar coordinate system for one acoustic signal (X (t)); The step of plotting dots in the polar coordinate system is repeated for a predetermined time, and the abnormality of the monitored object is diagnosed based on the dot pattern obtained as a result.

In the case of diagnosing the abnormality of the object to be monitored by the above-mentioned abnormality diagnosing method, the obtained dot pattern is visually displayed and the previously acquired normal time It is also possible to compare the dot pattern with the dot pattern at the time of diagnosis to visually diagnose the abnormality of the monitored object, or claim 5.
As described in, by using a suitable pattern recognition method, the dot pattern obtained is pattern-recognized, the dot pattern at the time of normal and the dot pattern at the time of pre-acquisition are compared, and the diagnosis is performed. When there is a deviation of a predetermined value or more between the time dot pattern and the normal dot pattern, the monitoring target may be diagnosed as abnormal.

Further, according to a third aspect of the present invention, the sound collecting device collects sounds generated by a plurality of objects to be monitored installed in a large facility space, and based on the sound signals. A method is provided for identifying a monitored object for abnormal operation. This method comprises the steps of: dividing the large facility space into a plurality of smaller facility spaces each including a plurality of monitored objects; In the equipment space, a step of sampling the acoustic signal at a predetermined cycle; a step of setting a fluctuation width of the acoustic signal sampled in the step as a reference value; an acoustic signal (X) sampled at a certain time (t). In a polar coordinate system having a radius of (t)) relative to the reference value (A (i)),
One acoustic signal (X (t)) is obtained by converting a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt into argument angles (Θ (i), Φ (i)). Plotting at least two dots (a (i), b (i)) that are line-symmetric with respect to at least one start line of the polar coordinate system with respect to; Repeating over time, and based on the dot pattern obtained as a result, identifying a small-area equipment space that includes an abnormal operation monitoring target; and including in the small-area equipment space identified in the step. And a step of specifying an abnormal operation monitoring target from a plurality of monitoring targets.

[0012] In the above method, as described in claim 7, before specifying the object to be monitored for abnormal operation, the small equipment space including the object to be monitored for abnormal operation is further subdivided. The step of dividing the space again and narrowing it down and narrowing down the equipment space including the object to be monitored for abnormal operation may be repeated as many times as necessary.

In the methods according to the second and third aspects, the polar coordinate system used to obtain the dot pattern is divided into a plurality of symmetrical regions by a plurality of (n) starting lines, and each starting line is divided into a plurality of regions. For example, by plotting two dots (a (i), b (i)) that are line symmetric with respect to each other, for example, by plotting dots with respect to six axes of symmetry (start line), A crystalline dot pattern is obtained, and the normal pattern and the abnormal pattern can be easily and reliably distinguished from each other visually or by pattern recognition without setting a numerical initial value.

[0014]

BEST MODE FOR CARRYING OUT THE INVENTION Preferred embodiments of an abnormality diagnosis apparatus and method according to the present invention will be described in detail below with reference to the accompanying drawings.

First, referring to FIG. 1, the first aspect of the present invention will be described.
The configuration of the abnormality diagnosis device 10 according to the embodiment of the present invention will be described. Reference numeral 12 is a fan filter unit (FF) that is a monitored object including a rotation mechanism such as a fan motor.
U), which is an equipment device installed in an arbitrary equipment space such as a clean room ceiling (not shown). 14
Is a sound collecting device such as a microphone that collects sound generated from the fan filter unit 12. In the illustrated example, the microphone 14 is arranged immediately above the portion 12a where the rotation mechanism of the fan filter unit is installed, but as described later, according to the present embodiment, the microphone 14 collects the sound. Since the generated acoustic signal is standardized, the attenuation of the acoustic signal due to the distance between the monitored object 12 and the microphone 14 is canceled out. Therefore, when diagnosing the same equipment, it can be considered that the sound collection position by the microphone 14 has little influence on the shape of the dot pattern obtained by the present embodiment. Therefore, according to the present embodiment. It is not necessary to strictly define the sound collection position, and it is not necessary to particularly amplify the collected sound signal.

The acoustic signal collected by the microphone 14 is measured (sampled) by a sampling means such as a sound level meter 16 at a predetermined cycle, data-converted by an A / D converter 18, and a signal processing unit (SDP converter). ) 19
Sent to The signal processing unit 19 plots the sampled acoustic signal on a polar coordinate system as shown in FIG.
Get the dot pattern. In this way, the dot-patterned acoustic signal is displayed on the screen of the display device 20 such as a CRT, or printed out on the paper by using a printing means such as a printer. Then, as will be described later, the worker can easily distinguish the abnormal pattern from the normal pattern from the dot patterns visually displayed on these screens or paper surfaces.
When visually displaying the dot pattern,
If the normal dot pattern 20a and the diagnostic dot pattern 20b are displayed on the same surface, as shown in FIG. 5, the abnormal pattern can be identified more easily.

Next, referring to FIG. 2, the signal processing unit 1
9, the procedure for plotting a dot pattern of the sampled acoustic signal in the polar coordinate system will be described.
The dot pattern depiction method employed in the present embodiment is known as one of the chaotic graphic expressions that characterize local differences as opposite polarities, and is called “targeted dot pattern (SDP: Symmetrized)”.
Dot Patterns ”method. In addition, SDP
The law is a well-established graphic technique, and its contents are described in Clifford. A. I'm familiar with Pickover's "Computer Chaos Fractal" translated by Tokichiro Takahashi and Shozo Naito, published by Hakuyosha.
The detailed description will be omitted by citing the same document as a reference.

The target dot pattern (SDP) is a dot pattern obtained by plotting the correlation between the value X (t) at time t of the time series data and the value X (t + τ) at time t + τ in the polar coordinate system. The procedure for plotting the target dot pattern will be described with reference to FIG.
A set of data (X (t), X (t + τ)) sampled as a time waveform as shown in FIG.
It is plotted as (a1, a1 ') so as to be line-symmetric with respect to the starting line of the polar coordinate system as shown in (b), and further,
The starting line is rotated by the number of axes of symmetry, and a set of data is plotted for each starting line. For example, as shown in FIG. 3, if there are 6 axes of symmetry, it is possible to divide the polar coordinates into 6 target regions by the start line rotated by 60 degrees, and one set for each start line, 6 sets in total. It is possible to plot a set of 12 dots (a1, a1 ') to (a6, a6') in a polar coordinate system.

The declination angles Θ (i) and Φ (i) that are line-symmetrical to the radius A (i) in the polar coordinate system of the time series data X (i) discretized with a constant sampling time Δt are as follows. Converted by an expression.

[0020]

[Equation 1]

As is clear from the above equation, the dot impact points (A (i), Θ (i)), (A (i), Φ (i))
Has a time width L and a gain ζ as parameters. Therefore, it is necessary to optimize the time width L and the gain ζ in order to identify the abnormality from the time series data by SDP. The time width L and the gain ζ can be appropriately selected according to the frequency characteristics of the acoustic signal generated from the monitored object. For example, when the monitored object is a rotating machine such as FFU, the acoustic signal generated therefrom can be approximated by a periodic function: sin (2πft), for example, the fundamental frequency f = 550 Hz. ,
When Δt = 1 / 20000s, by setting the time width L to 5 to 6 steps and ζ to about 40, it is possible to obtain the spread of the SDP which can be easily visually identified.

As is clear from the above equation, the sampled acoustic signal has a fluctuation range (Xma) of the acoustic signal.
x-Xmin), the attenuation of the acoustic signal due to the distance between the monitored object and the microphone is canceled out. Therefore, when diagnosing the same equipment,
Since it can be considered that the sound collection position by the microphone has little influence on the shape of the dot pattern obtained by the present embodiment, according to the present embodiment, it is not necessary to strictly define the sound collection position. Further, there is no need to particularly amplify the collected acoustic signal. As for background noise, it is sufficient to recognize the tendency of sound as described later, and it is not necessary to take measures for it.

4 to 6 show a normal FFU and an abnormal FF.
An example in which SDP expression is performed on the sounds respectively generated from U by the abnormality diagnosis device according to the present embodiment will be shown. It should be noted that FIG. 4 shows a comparison between an FFU in which a strange noise is recognized and a normal FFU, and FIGS. 5 and 6 show a comparison between an FFU in which a strange noise is recognized and a normal FFU. An example is shown. In each case,
The FFU data in which abnormal noise is recognized is shown on the right side.

As can be seen from these figures, it is not possible to judge the difference between the sound signal in the normal case and the sound signal in the abnormal case from the graph in which the sound signal sampled by the microphone is simply represented as a time waveform. Have difficulty.
On the other hand, according to the SDP representation, a normal acoustic signal is clearly plotted on the axis of symmetry, whereas an abnormal acoustic signal has an ambiguous plot on the axis of symmetry. In the example, it can be seen that the dot pattern develops in a circle. As described above, according to the SDP expression by the abnormality diagnosis device according to the present embodiment, since the abnormal acoustic signal is expressed by the ambiguity of the expression, even a worker who has not undergone special training, It is possible to diagnose visually easily. At that time, as shown in FIGS. 4 to 6, if the normal dot pattern and the dot pattern at the time of diagnosis are simultaneously displayed on the same screen, it is possible to more easily determine whether the dot pattern is normal or abnormal. .

In the examples of FIGS. 4 to 6, the cause of the ambiguity in the SDP expression of the abnormal acoustic signal is as follows.
It is considered that when an abnormality occurs in the monitored object that is a rotating system, the multiple of the shaft rotation frequency and the vibration acceleration of the nonlinear component increase. Further, as in the example shown in FIG. 4, it is considered that the cause of the circular contour in the SDP expression of the abnormal acoustic signal is that the amplitude of a certain periodic function varies irregularly.

In the example shown in FIG. 1, the apparatus configuration for diagnosing the abnormality of one FFU is shown, but the present invention is not limited to this example. For example, as shown in FIG. 7, a large number of FFUs (U11 to UFU) are provided on the ceiling 32 of the clean room 30.
Umn) is installed. But each of these FFUs
If the microphones are individually installed or the individual abnormality diagnosis is performed, a large amount of labor is required at the initial cost. In this respect, according to the present invention, it is not necessary to individually diagnose an abnormality in each FFU, and it is possible to collectively diagnose a plurality of FFUs included in a certain range at the same time.

That is, according to the device and method of the present invention, even if sounds from a plurality of FFUs are simultaneously collected,
The acoustic signal can be regarded as a superposition of a plurality of periodic functions, and a plurality of FFUs included in a certain range.
The superposed acoustic signal generated from can be considered to represent a unique SDP. Therefore, if there is an abnormal operation among the FFUs included in the range, a change also appears in the superimposed acoustic signal, and it is possible to determine whether or not the abnormal FFU is included in the range. For example, in the illustrated example, the microphone 34 is movably attached to the ceiling by a driving device 36, and for example, nine FFUs are provided.
(U11-U13, U21-U23, U31-U33)
An abnormality can be diagnosed by using a region including a as a diagnostic unit. Then, the apparatus and method of the present invention can specify the area containing the abnormal FFU and then further narrow it down to easily specify the abnormal FFU. Further, it is also possible to provide the same effect as described above by installing an appropriate number of microphones in advance on a wall portion or the like at a predetermined interval, providing the computer side channels by the number, and switching the channels at any time.

As described above, according to the present invention, even when a large number of objects to be monitored such as FFUs are installed in a large facility space such as the ceiling of a clean room, the large facility space is maintained. , An equipment space containing abnormal monitoring objects can be easily obtained by dividing the equipment space into smaller equipment spaces each containing a plurality of objects to be monitored and expressing the acoustic signal generated from each small equipment space by SDP. Can be narrowed down. Needless to say, it is possible to narrow down the equipment space including the abnormal monitored object in multiple stages. And after being narrowed down to some extent,
It is possible to specify a monitored object that is performing an abnormal operation from the specified equipment space of the small area.

Next, with reference to FIGS. 8 and 9, a diagnosis flow for actually identifying a small area equipment space containing an abnormal FFU from the large area equipment space will be described.

First, as shown in FIG. 8, as preprocessing,
SDP storage processing in normal time is performed. That is, after the microphone is installed in the equipment space of a predetermined small area (step S81), the measurement of the acoustic signal is started (step S8).
2) A / D-convert the sampled acoustic signal at dT intervals for T seconds (step S83) to obtain a digital signal (step S84). This signal is SDP-displayed by the method described above (step S85), and the result is stored as the SDP at the normal time (step S8).
6).

Next, the diagnostic routine for the rotating equipment shown in FIG. 9 is started. First, move to the first measurement location (step S91) and install a microphone (step S9).
2). Then, the measurement of the acoustic signal is started in the installation space (step S93), the sampled acoustic signal is A / D converted at the dT interval for T seconds (step S94), and a digital signal is obtained (step S95).
This signal is SDP-displayed by the method described above (step S96), and is compared with the previously stored normal SDP in the preprocessing shown in FIG. 8 (step S97). Then, if there is a difference, it is determined that there is an abnormality in the measurement space (step S98), if there is no difference, it is determined that the measurement space is normal (step S99), and the operation is performed over the entire area. By doing so (step S10
0), the diagnosis is completed.

In the routines shown in FIGS. 8 and 9, the case where the abnormality diagnosis is performed in real time at the measurement site is shown. However, as in the routine shown in FIG. It is also possible to make a measurement and later perform an abnormality diagnosis while reproducing a recorded acoustic signal.

The preferred embodiments of the abnormality diagnosis apparatus and method according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to the above examples. It is obvious to those skilled in the art that various changes and modifications can be conceived within the scope of the technical idea described in the claims, and naturally, these are also within the technical scope of the present invention. It is understood that it belongs.

For example, in the description of the above embodiment, an example in which the abnormality diagnosing apparatus and method according to the present invention are applied in order to determine whether the operation of the monitored object is normal or abnormal is shown. However, it is empirically known that a specific SDP expression appears for a specific failure. Therefore, by knowing the characteristics of the SDP expression for each failure cause in advance, the SDP expression for each failure cause and the SDP expression at the time of diagnosis It is also possible to make a determination as to the cause of the failure by comparing it with the expression.

In the description of the above embodiment, an example in which an SDP expression is developed on the screen of a display device such as a CRT and a worker visually diagnoses abnormality has been described. It is also possible to configure so as to automatically perform abnormality diagnosis.

An example of a method for comparing SDP expressions in a normal state and an abnormal state by pattern recognition will be described below with reference to FIG.
Describing with reference to, first, the SDP in the normal state and the SDP in the diagnosis are prepared, and the coordinate position of the SDP is developed on the matrix. Specifically, the coordinates for one axis of SDP are
For example, it is divided into a matrix of 1000 × 1000. Normal SDP matrix: NSD [1000 × 1
000] SDP matrix at abnormal time: DSD [1000 × 1
000]

If the initial value of the matrix is 0 and there is a plot on the coordinate axis, the value of the matrix corresponding to the coordinate is input as 1 and the plot of SDP is expanded into the matrix. In this way, the presence / absence of plots for the normal SDP and the abnormal SDP is expanded into a matrix.

Then, the normal SDP is subtracted from the abnormal SDP developed in the matrix to obtain the deviation matrix HSD. HSD [i, j] = DSD [i, j] -NSD [i, j] However, when DSD [i, j] -NSD [i, j] =-1, it is regarded as 0. This is because it can be determined that the SDP pattern at the abnormal time is formed by moving the plot position at the normal time to another coordinate. That is, the abnormal pattern is plotted at coordinates that are not in the normal pattern.

Then, the deviation matrix is reconverted to SDP to obtain the deviation SDP. Then, the abnormality can be identified by pattern-matching the screen processing between the shape of the deviation SDP and the reference SDP indicating the abnormality.

In the description of the above embodiment, a rotary system such as an FFU is taken as an example of the object to be monitored, but the abnormality diagnosis device and method according to the present invention is not limited to such an example. For example, even in a motion system other than a rotary system such as a reciprocating engine or a pump, the acoustic signals generated from the motion system have their own SDP expressions. It can also be applied to determine abnormalities of various motor systems.

[0041]

As described above, according to the present invention,
Since the difference between the localized acoustic signals can be expressed globally, it is possible to visually and easily diagnose the abnormality of the monitored object without requiring much specialized knowledge.
Further, according to the present invention, the result can be obtained by a simple operation of measuring an acoustic signal and drawing an SDP.
The processing required for diagnosis is extremely simple, and a simple abnormality diagnosis device can be constructed.

Further, according to the present invention, as a method for diagnosing an abnormality, a comparison is made between the time of diagnosis and the time of normality.
A graphic pattern by P is required, but a numerical limit value is not required, and there is no difficulty in acquiring the system.
Furthermore, if one piece of SDP data of the equipment related to the diagnosis is prepared in advance, it can be used universally for each facility.

Further, according to the present invention, the measured acoustic signal is standardized when plotting the SDP, so that the attenuation of the acoustic signal depending on the distance between the sound source and the sound collecting means is canceled. Therefore, when diagnosing the same device, the SDP shape is unlikely to be affected by the distance between the sound collector and the sound source, so that the diagnosis can be performed easily and accurately.

Further, according to the present invention, even if there are a large number of objects to be monitored in a wide area, by expressing the acoustic signals generated from a predetermined collective space by SDP, an abnormality can occur in that space. Since it is possible to determine whether or not there is any, it is possible to dramatically reduce the amount of work as compared with the case where the abnormality diagnosis of the monitoring target is individually performed as in the conventional case.

[Brief description of drawings]

FIG. 1 is a system configuration diagram showing an embodiment of an abnormality diagnosis device according to the present invention.

FIG. 2 is a graph showing an acoustic signal measured by the abnormality diagnosis device according to the present invention, (a) shows a time waveform of the acoustic signal, and (b) shows a state of the acoustic signal plotted in polar coordinates. ing.

FIG. 3 is an explanatory diagram showing an example of an SDP expression of an acoustic signal plotted line-symmetrically with respect to a plurality of polar symmetry axes.

FIG. 4 is a diagram showing time waveforms and SDP expressions of sound signals of a normal FFU and an abnormal FFU measured by the abnormality diagnosis device and method according to the present invention.

FIG. 5 is a chart showing time waveforms and SDP expressions of sound signals of a normal FFU and an abnormal FFU measured by the abnormality diagnosis device and method according to the present invention.

FIG. 6 is a diagram showing time waveforms and SDP expressions of sound signals of a normal FFU and an abnormal FFU measured by the abnormality diagnosis device and method according to the present invention.

FIG. 7 is an explanatory diagram showing an embodiment in which the abnormality diagnosis device according to the present invention is applied to a large number of FFUs installed in a wide facility space on the ceiling of a clean room.

FIG. 8 is a flowchart showing an example of an abnormality diagnosis method according to the present invention.

FIG. 9 is a flowchart showing an example of an abnormality diagnosis method according to the present invention.

FIG. 10 is a flow chart showing an example of an abnormality diagnosis method according to the present invention.

FIG. 11 is an explanatory diagram showing a case in which a pattern recognition technique is applied to the abnormality diagnosis device and method according to the present invention.

[Explanation of symbols]

 12 FFU 14 Microphone 16 Sound level meter 18 A / D converter 19 Signal processing unit 20 Display device 20a Normal pattern 20b Abnormal pattern

Claims (7)

[Claims] 1. 1 or 2 installed in an arbitrary equipment space
An abnormality diagnostic device for collecting the sound generated by the above-mentioned monitored object by a sound collector and diagnosing an abnormality of the monitored object based on the acoustic signal: sampling the acoustic signal at a predetermined cycle. Sampling means for setting the fluctuation width of the acoustic signal sampled over a certain time interval as a reference value; and for the reference value of the acoustic signal (X (t)) sampled at a certain time (t) In a polar coordinate system having a relative magnitude (A (i)) as a radius, a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt is used as declination angles (Θ (i), Φ).
(I)) to convert one acoustic signal (X
For (t), at least two dots (a) that are line-symmetric with respect to at least one start line of the polar coordinate system.
(I), b (i)), a plotting means for plotting; and a display means for visually displaying the dot pattern plotted by the plotting means; and according to the dot pattern displayed by the display means. An abnormality diagnosing device for diagnosing an abnormality of the monitored object. 2. 1 or 2 installed in any facility space
An abnormality diagnostic device for collecting the sound generated by the above-mentioned monitored object by a sound collector and diagnosing an abnormality of the monitored object based on the acoustic signal: sampling the acoustic signal at a predetermined cycle. Sampling means for setting the fluctuation width of the acoustic signal sampled over a certain time interval as a reference value; and for the reference value of the acoustic signal (X (t)) sampled at a certain time (t) In a polar coordinate system having a relative magnitude (A (i)) as a radius, a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt is used as declination angles (Θ (i), Φ).
(I)) to convert one acoustic signal (X
For (t), at least two dots (a) that are line-symmetric with respect to at least one start line of the polar coordinate system.
(I), b (i)) plotting means; pattern recognition means for recognizing the dot pattern plotted by the plotting means; dot pattern for diagnosis, which is pattern recognized by the pattern recognizing means, in advance Compared with the acquired normal dot pattern, if there is a deviation of a predetermined value or more between the diagnostic dot pattern and the normal dot pattern,
An abnormality diagnosis device comprising: a comparative diagnosis means for diagnosing that the monitored object is abnormal. 3. 1 or 2 installed in any facility space
An abnormality diagnosis method for collecting the sound generated by the above-mentioned monitored object by a sound collector and diagnosing an abnormality of the monitored object based on the acoustic signal: sampling the acoustic signal at a predetermined cycle. A step of setting the fluctuation width of the acoustic signal sampled in the step as a reference value; a relative magnitude of the acoustic signal (X (t)) sampled at a certain time (t) with respect to the reference value. In a polar coordinate system having a radius of (A (i)), a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt is converted into an argument (Θ (i), Φ (i)). By doing so, at least two dots (a (i), b (i)) that are line-symmetric with respect to at least one start line of the polar coordinate system with respect to one acoustic signal (X (t))
Plotting dots in the polar coordinate system, repeating the step of plotting dots in the polar coordinate system for a predetermined time, and diagnosing the abnormality of the monitored object based on the dot pattern obtained as a result. And the abnormality diagnosis method. 4. The step of diagnosing an abnormality of the monitored object visually displays the obtained dot pattern, and compares a previously obtained normal dot pattern with a diagnostic dot pattern. The abnormality diagnosis method according to claim 3, wherein the abnormality is diagnosed in the monitored object. 5. The step of diagnosing an abnormality of the monitored object, the pattern recognition of the obtained dot pattern, pattern comparison of the dot pattern at the time of normal and the dot pattern at the time of pre-acquired, pattern comparison, When the deviation between the dot pattern at the time of diagnosis and the dot pattern at the time of normality is greater than or equal to a predetermined value, it is diagnosed that the monitored object is abnormal. The abnormality diagnosis method according to Item 3. 6. A method of collecting sound generated by a plurality of objects to be monitored installed in a global facility space by a sound collector, and identifying an object to be monitored for abnormal operation based on the sound signal. And: dividing the global equipment space into a plurality of smaller equipment spaces each including a plurality of objects to be monitored, and narrowing down; A step of sampling in a cycle; a step of setting a fluctuation range of the acoustic signal sampled in the step as a reference value; an acoustic signal (X
(T)) relative size (A) with respect to the reference value
(I)) in a polar coordinate system, converting a value obtained by discretizing the acoustic signal (X (t)) over a predetermined time interval Δt into argument angles (Θ (i), Φ (i)). Plotting at least two dots (a (i), b (i)) that are line-symmetric with respect to at least one start line of the polar coordinate system for one acoustic signal (X (t)); Repeating the step of plotting dots in the polar coordinate system for a predetermined time, and specifying a small equipment space containing an object to be monitored for abnormal operation based on the dot pattern obtained as a result; And a step of specifying a monitoring target object of abnormal operation from a plurality of monitoring target objects included in the small equipment space specified in 1. 7. Before specifying an object to be monitored for abnormal operation,
The step of narrowing down the equipment space containing the abnormal operation monitoring target by dividing the small equipment space containing the abnormal operation monitoring object into smaller equipment spaces again and narrowing it down The abnormality diagnosis method according to claim 6, wherein the abnormality diagnosis method is repeated.